rebase eval test w/ tool_runtime fixtures (#773)

# What does this PR do?

- fix eval tests to include tool_runtime fixtures
- rebase eval for extracting memory retrieval context

## Test Plan

```
pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio llama_stack/providers/tests/eval/test_eval.py
pytest -v -s -m braintrust_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py
```
- With notebook:
https://gist.github.com/yanxi0830/1260a6cb7ec42498a195b88422462a34

## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

llama_stack/providers/inline/eval/meta_reference/eval.py

@@ -16,6 +16,9 @@ from llama_stack.apis.scoring import Scoring
 from llama_stack.distribution.datatypes import Api
 from llama_stack.providers.datatypes import EvalTasksProtocolPrivate
 
+from llama_stack.providers.inline.agents.meta_reference.agent_instance import (
+    MEMORY_QUERY_TOOL,
+)
 from llama_stack.providers.utils.common.data_schema_validator import (
     ColumnName,
     get_valid_schemas,
@@ -146,8 +149,12 @@ class MetaReferenceEvalImpl(
             # check if there's a memory retrieval step and extract the context
             memory_rag_context = None
             for step in final_event.turn.steps:
-                if step.step_type == StepType.memory_retrieval.value:
-                    memory_rag_context = " ".join(x.text for x in step.inserted_context)
+                if step.step_type == StepType.tool_execution.value:
+                    for tool_response in step.tool_responses:
+                        if tool_response.tool_name == MEMORY_QUERY_TOOL:
+                            memory_rag_context = " ".join(
+                                x.text for x in tool_response.content
+                            )
 
             agent_generation = {}
             agent_generation[ColumnName.generated_answer.value] = (